mlsanityData to 14 Oct 2026

Frequency-Enhanced Diffusion Models: Curriculum-Guided Semantic Alignment for Zero-Shot Skeleton Action Recognition

arXiv 2604.09063 ↗First posted 10 Apr 2026cs.CV cs.AIcited by 2

On the map: Diffusion models → Video generation

Abstract (arXiv)

Human action recognition is pivotal in computer vision, with applications ranging from surveillance to human-robot interaction. Despite the effectiveness of supervised skeleton-based methods, their reliance on exhaustive annotation limits generalization to novel actions. Zero-Shot Skeleton Action Recognition (ZSAR) emerges as a promising paradigm, yet it faces challenges due to the spectral bias of diffusion models, which oversmooth high-frequency dynamics. Here, we propose Frequency-Aware Diffusion for Skeleton-Text Matching (FDSM), integrating a Semantic-Guided Spectral Residual Module, a Timestep-Adaptive Spectral Loss, and Curriculum-based Semantic Abstraction to address these challenges. Our approach effectively recovers fine-grained motion details, achieving state-of-the-art performance on NTU RGB+D, PKU-MMD, and Kinetics-skeleton datasets. Code has been made available at https://github.com/yuzhi535/FDSM. Project homepage: https://yuzhi535.github.io/FDSM.github.io/

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in Video generation, one of 14 directions in Diffusion models. Builds on 50 of its 81 references that are in the map. First posted on arXiv 10 Apr 2026.

Builds on

50 of 81 references.

Closest ancestors · 4

Same direction, newest first

  1. 2024Bridging the Skeleton-Text Modality Gap: Diffusion-Powered Modality Alignment for Zero-shot Skeleton-based Action Recognition16 Nov
  2. 2024Diff-Tracker: Text-to-Image Diffusion Models are Unsupervised Trackers11 Jul
  3. 2022Human Motion Diffusion Model29 Sep
  4. 2022MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model31 Aug

Other references · 46

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  4. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  5. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  6. 2023GPT-4 Technical Reportcited by 18,396
  7. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  8. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  9. 2020Denoising Diffusion Implicit Modelscited by 9,781
  10. 2022Scalable Diffusion Models with Transformerscited by 6,054
  11. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
  12. 2017The Kinetics Human Action Video Datasetcited by 1,909
34 more
  1. 2020Knowledge Distillation: A Surveycited by 1,603
  2. 2018On the Spectral Bias of Neural Networkscited by 1,341
  3. 2018Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 1,209
  4. 2016NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysiscited by 686
  5. 2022Vision Transformer Adapter for Dense Predictionscited by 565
  6. 2019NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understandingcited by 533
  7. 2020Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognitioncited by 343
  8. 2021Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognitioncited by 322
  9. 2022Perception Prioritized Training of Diffusion Modelscited by 303
  10. 2021Revisiting Skeleton-based Action Recognitioncited by 257
  11. 2018Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoderscited by 206
  12. 2016Spatio-Temporal LSTM with Trust Gates for 3D Human Action Recognitioncited by 143
  13. 2017View Adaptive Recurrent Neural Networks for High Performance Human Action Recognition from Skeleton Datacited by 105
  14. 2017PKU-MMD: A Large Scale Benchmark for Continuous Multi-Modal Human Action Understandingcited by 101
  15. 2019Fine-Grained Action Retrieval Through Multiple Parts-of-Speech Embeddingscited by 101
  16. 2022Inception Transformercited by 99
  17. 2017Learning Robust Visual-Semantic Embeddingscited by 56
  18. 2024SkateFormer: Skeletal-Temporal Transformer for Human Action Recognitioncited by 47
  19. 2022IGFormer: Interaction Graph Transformer for Skeleton-based Human Interaction Recognitioncited by 31
  20. 2021Syntactically Guided Generative Embeddings for Zero-Shot Skeleton Action Recognitioncited by 24
  21. 2023Zero-shot Skeleton-based Action Recognition via Mutual Information Estimation and Maximizationcited by 24
  22. 2024Part-aware Unified Representation of Language and Skeleton for Zero-shot Action Recognitioncited by 23
  23. 2024Fine-Grained Side Information Guided Dual-Prompts for Zero-Shot Skeleton Action Recognitioncited by 19
  24. 2024SA-DVAE: Improving Zero-Shot Skeleton-Based Action Recognition by Disentangled Variational Autoencoderscited by 19
  25. 2022Distilling Inter-Class Distance for Semantic Segmentationcited by 16
  26. 2024Frequency Guidance Matters: Skeletal Action Recognition by Frequency-Aware Mixed Transformercited by 15
  27. 2023Scene-aware Human Pose Generation using Transformercited by 9
  28. 2023Multi-Semantic Fusion Model for Generalized Zero-Shot Skeleton-Based Action Recognitioncited by 9
  29. 2024Zero-Shot Skeleton-based Action Recognition with Dual Visual-Text Alignmentcited by 9
  30. 2023Ske2Grid: Skeleton-to-Grid Representation Learning for Action Recognitioncited by 7
  31. 2024An Information Compensation Framework for Zero-Shot Skeleton-based Action Recognitioncited by 7
  32. 2025Frequency-Semantic Enhanced Variational Autoencoder for Zero-Shot Skeleton-based Action Recognitioncited by 6
  33. 2025Informative Sample Selection Model for Skeleton-based Action Recognition with Limited Training Samplescited by 4
  34. 2026EFSI-DETR: Efficient Frequency-Semantic Integration for Real-Time Small Object Detection in UAV Imagerycited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Leveraging Text-to-Image Diffusion Models for Unsupervised Visual Object Trackingcited by 1
  2. 2026Visual Anchoring in Diffusion: Multimodal Zero-Shot Skeleton Action Recognitioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Learning by Neighbor-Aware Semantics, Deciding by Open-form Flows: Towards Robust Zero-Shot Skeleton Action Recognition
  2. 2025CoCoDiff: Diversifying Skeleton Action Features via Coarse-Fine Text-Co-Guided Latent Diffusion
  3. 2024Neuron: Learning Context-Aware Evolving Representations for Zero-Shot Skeleton Action Recognition
  4. 2025Zero-Shot Skeleton-Based Action Recognition With Prototype-Guided Feature Alignment
  5. 2023Spatial-temporal Transformer-guided Diffusion based Data Augmentation for Efficient Skeleton-based Action Recognition
  6. 2025Boosting Skeleton-based Zero-Shot Action Recognition with Training-Free Test-Time Adaptation
  7. 2024MacDiff: Unified Skeleton Modeling with Masked Conditional Diffusion
  8. 2026ProMoDD: Dataset Distillation for 3D Human Motion via Prototype-Conditioned Diffusion Models